AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Efficient Loss-Based Decoding on Graphs for Extreme Classification

Itay Evron, Edward Moroshko, Koby Crammer

NeurIPS 2018 · Learning theory and algorithms › Prediction and decision losses · approach: Consistency of surrogate losses · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Increase trellis slice width (ablation)W-LTLS · sectortest accuracy (%): 88.45 -> 94.88Improved
Increase trellis slice width (ablation)W-LTLS · aloi.bintest accuracy (%): 82.24 -> 95.16Improved
Increase trellis slice width (ablation)W-LTLS · imageNettest accuracy (%): 0.75 -> 12.60Improved
Increase trellis slice width (ablation)W-LTLS · Dmoztest accuracy (%): 23.04 -> 38.89Improved
Increase trellis slice width (ablation)W-LTLS · LSHTC1test accuracy (%): 9.50 -> 22.47Improved
Use exponential loss for loss-based decoding instead of squared loss (ablation)W-LTLS · five extreme-classification datasetstest accuracyImproved
Increase slice width, making induced binary subproblems less balanced (ablation)W-LTLS · all five datasetsaverage binary training lossImproved
Prune weights in [-lambda, lambda] (ablation)W-LTLS · sparse datasets excluding imageNettest accuracyNo clear effect
Use wider graphs before post-pruning (ablation)W-LTLS · sparse datasets excluding imageNetmodel sizeImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy